RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-22 10:42:39 +01:00
Code Issues Projects Releases Wiki Activity

[LSR] Handle case 1*reg => reg. PR50918

Browse Source 
This patch addresses assertion failure in case when the only found formula for LSR
is `1*reg => reg` which was supposed to be an impossible situation, however there
is a test that shows it is possible.

In this case, we can use scale register with scale of 1 as the missing base register.

Reviewed By: huihuiz, reames
Differential Revision: https://reviews.llvm.org/D105009
This commit is contained in:
Max Kazantsev 2021-07-16 11:31:15 +07:00
parent 539761ef24
commit e4a04110a4
2 changed files with 51 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
lib/Transforms/Scalar/LoopStrengthReduce.cpp
View File

@ -511,9 +511,16 @@ bool Formula::isCanonical(const Loop &L) const {
void Formula::canonicalize(const Loop &L) {
if (isCanonical(L))
return;
// So far we did not need this case. This is easy to implement but it is
// useless to maintain dead code. Beside it could hurt compile time.
assert(!BaseRegs.empty() && "1*reg => reg, should not be needed.");
if (BaseRegs.empty()) {
// No base reg? Use scale reg with scale = 1 as such.
assert(ScaledReg && "Expected 1*reg => reg");
assert(Scale == 1 && "Expected 1*reg => reg");
BaseRegs.push_back(ScaledReg);
Scale = 0;
ScaledReg = nullptr;
return;
}
// Keep the invariant sum in BaseRegs and one of the variant sum in ScaledReg.
if (!ScaledReg) {

41
test/Transforms/LoopStrengthReduce/pr50918.ll Normal file
View File

@ -0,0 +1,41 @@
; RUN: opt -S -loop-reduce < %s | FileCheck %s
;
; Make sure we don't fail an assertion here.
target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128-ni:1-p2:32:8:8:32-ni:2"
target triple = "x86_64-unknown-linux-gnu"
define void @test() {
; CHECK-LABEL: test
bb:
br label %bb1
bb1: ; preds = %bb12, %bb
%tmp2 = phi i64 [ 94, %bb ], [ %tmp20, %bb12 ]
%tmp3 = phi i32 [ -28407, %bb ], [ %tmp23, %bb12 ]
%tmp4 = trunc i64 %tmp2 to i32
%tmp5 = add i32 %tmp3, %tmp4
%tmp6 = mul i32 undef, %tmp5
%tmp7 = sub i32 %tmp6, %tmp5
%tmp8 = shl i32 %tmp7, 1
%tmp9 = add i32 %tmp8, %tmp3
%tmp10 = add i32 %tmp9, %tmp4
%tmp11 = shl i32 %tmp10, 1
br label %bb21
bb12: ; preds = %bb21
%tmp13 = mul i32 %tmp22, -101
%tmp14 = add i32 %tmp22, 2
%tmp15 = add i32 %tmp14, %tmp13
%tmp16 = trunc i32 %tmp15 to i8
%tmp17 = shl i8 %tmp16, 5
%tmp18 = add i8 %tmp17, 64
%tmp19 = sext i8 %tmp18 to i32
%tmp20 = add nsw i64 %tmp2, -3
br label %bb1
bb21: ; preds = %bb21, %bb1
%tmp22 = phi i32 [ %tmp11, %bb1 ], [ %tmp23, %bb21 ]
%tmp23 = add i32 %tmp22, 1
br i1 false, label %bb12, label %bb21
}